通过分解图像组件提升异常检测精度，有效识别组合型异常。
Component-Based Out-of-Distribution Detection
- 将输入图像分解为功能组件，避免全局表征掩盖局部异常信号。
- 提出组件位移分数与组合一致性分数，在多个数据集上提升检测效果。
- 无需训练，适合对细粒度异常敏感的应用场景。
分布外（OOD）检测需在细微变化中保持敏感，又不因分布内自然多样性而误报。然而，全局表征会压制局部异常线索，基于补丁的方法则易受虚假相关性和噪声干扰，且难以检测由有效分布内组件构成的组合型OOD。受部件识别理论启发，我们提出无需训练的组件式OOD检测框架CoOD，通过将输入分解为功能组件来克服上述局限。具体地，定义组件位移分数（CSS）以检测局部外观变化，组合一致性分数（CCS）以识别跨组件的组合不一致。实验证明，CoOD在粗粒度与细粒度的OOD检测任务上均取得稳定提升。
原文摘要 · Abstract (English)
Out-of-Distribution (OOD) detection requires sensitivity to subtle shifts without overreacting to natural In-Distribution (ID) diversity. However, from the viewpoint of detection granularity, global representation inevitably suppress local OOD cues, while patch-based methods are unstable due to entangled spurious-correlation and noise. And neither them is effective in detecting compositional OODs composed of valid ID components. Inspired by recognition-by-components theory, we present a training-free Component-Based OOD Detection (CoOD) framework that addresses the existing limitations by decomposing inputs into functional components. To instantiate CoOD, we derive Component Shift Score (CSS) to detect local appearance shifts, and Compositional Consistency Score (CCS) to identify cross-component compositional inconsistencies. Empirically, CoOD achieves consistent improvements on both coarse- and fine-grained OOD detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。